发的都是原图下载后可以直接识别！！！！
更多我的 模型 Shakker AI - Premium Stable Diffusion Model Hub
TG:https://t.me/+OAGBz7JQh9xmM2Jl
我创建了一个lora和发图交流的qq群欢迎大家加入：817686141
求求大家的返图和星星
白色蕾丝吊带内衣的复杂程度随着权重增加而增加我推荐0.7左右最好
连身袜s2我推荐权重0.6-0.8，想要有较好的背景泛化最好是0.75这样。
很多人说模型没有头部，比起分层去除脸部数据我更倾向直接把脸部先去除，需要脸部可以将我原图入sd识别，或者加上脸部的描述，如发型，发色，眼睛颜色之类的。
紫色诱惑我推荐权重0.8-1，提示词默认的大腿袜也是紫色的，封面是使用了cn
关于恶魔服饰，低权重的情况下需要的触发词比较多，可以查看我的原图提取触发词。
这是我情趣服装系列之一，如你所见有很强的色情能力，lora质量还行，脸部我推荐用After Detailer插件，能生成更好的脸部。主要是网络素材练成，本身不带脸部数据，最好加上手部动作的描述，不然容易摸脸动作。权重给0.6-0.8，如果你有lora分层插件的化可以使用：clothe:1,1,1,1,1,0,0.2,0,0.8,1,1,0.2,0,0,0,0,0 ,会得到更好的效果，请关注我后续我会发上更多模型。如果你喜欢我的模型系列的话。帮我点个赞，喜欢我的lora的话可以给我发电支持我一下哦，你的支持是我前进的动力。
this is one of my sex clothing collections,as you can see, there is a strong erotic ability,lora's quality is good,i recommend using the after detailer plugin for the face,can generate better facial features,mainly through the refinement of online materials,without facial data itself,it's best to include a description of hand movements,otherwise, it's easy to touch your face,weighted between 0.6 and 0.8,if you have a lora layered plugin, you can use the default layered out0.5,will achieve better results,please follow me and i will post more models in the future,if you like my model series,please give me a like,if you like my lora, you can give me a power generation to support me,your support is the driving force for me to move forward,
Description
FAQ
Comments (10)
The prompts for all images in https://civitai.com/models/119899?modelVersionId=195130 appear to be missing
(masterpiece:1.3),(best quality:1.3),(photorealistic:1.4),(full body:1.2),(cityscape:1.3),see-through,(street:1.4),(ultra detailed:1.3),unity 8k wallpaper,1girl,solo,black hair,legs,<lora:smbody_20230910012123-000019:0.7>,(large breasts:1.2),<lora:heyehua-000009:0.2>,
Negative prompt: easynegative,(badhandv4:1.2),(worst quality:2),(low quality:2),(normal quality:2),lowres,bad anatomy,bad hands,normal quality,((monochrome)),((grayscale)),Freckles,(phone:1.2),Too many hands and feet,bad-picturenegativeembeddingforChilloutMix_75VectorVersion,
Steps: 20, Sampler: DPM++ 2M alt Karras, CFG scale: 7, Seed: 1724101354, Size: 440x768, Model hash: 6bf3cb936a, Model: tauronHybridMix_tauhybridRealV21, VAE hash: 551eac7037, VAE: vae-ft-mse-840000-ema-pruned.ckpt, Denoising strength: 0.35, Clip skip: 2, ADetailer model: face_yolov8n.pt, ADetailer confidence: 0.3, ADetailer dilate/erode: 32, ADetailer mask blur: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer version: 23.10.0, ControlNet 0: "Module: none, Model: control_v11p_sd15_openpose [cab727d4], Weight: 0.95, Resize Mode: Crop and Resize, Low Vram: False, Guidance Start: 0, Guidance End: 1, Pixel Perfect: True, Control Mode: ControlNet is more important", Hires upscale: 2, Hires steps: 9, Hires upscaler: 4x-UltraSharp, Lora hashes: "smbody_20230910012123-000019: 7ffa851f00a2, heyehua-000009: fef194d46e9f", Dynamic thresholding enabled: True, Mimic scale: 7, Separate Feature Channels: True, Scaling Startpoint: MEAN, Variability Measure: AD, Interpolate Phi: 1, Threshold percentile: 100, TI hashes: "easynegative: c74b4e810b03, badhandv4: 5e40d722fc3d, bad-picturenegativeembeddingforChilloutMix_75VectorVersion: 7d9cc5f549d7", Version: v1.6.0
missing prompts?
原图无法上传
(masterpiece:1.3),(best quality:1.3),(photorealistic:1.4),(full body:1.2),(cityscape:1.3),see-through,(street:1.4),(ultra detailed:1.3),unity 8k wallpaper,1girl,solo,black hair,legs,<lora:smbody_20230910012123-000019:0.7>,(large breasts:1.2),<lora:heyehua-000009:0.2>,
Negative prompt: easynegative,(badhandv4:1.2),(worst quality:2),(low quality:2),(normal quality:2),lowres,bad anatomy,bad hands,normal quality,((monochrome)),((grayscale)),Freckles,(phone:1.2),Too many hands and feet,bad-picturenegativeembeddingforChilloutMix_75VectorVersion,
Steps: 20, Sampler: DPM++ 2M alt Karras, CFG scale: 7, Seed: 1724101354, Size: 440x768, Model hash: 6bf3cb936a, Model: tauronHybridMix_tauhybridRealV21, VAE hash: 551eac7037, VAE: vae-ft-mse-840000-ema-pruned.ckpt, Denoising strength: 0.35, Clip skip: 2, ADetailer model: face_yolov8n.pt, ADetailer confidence: 0.3, ADetailer dilate/erode: 32, ADetailer mask blur: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer version: 23.10.0, ControlNet 0: "Module: none, Model: control_v11p_sd15_openpose [cab727d4], Weight: 0.95, Resize Mode: Crop and Resize, Low Vram: False, Guidance Start: 0, Guidance End: 1, Pixel Perfect: True, Control Mode: ControlNet is more important", Hires upscale: 2, Hires steps: 9, Hires upscaler: 4x-UltraSharp, Lora hashes: "smbody_20230910012123-000019: 7ffa851f00a2, heyehua-000009: fef194d46e9f", Dynamic thresholding enabled: True, Mimic scale: 7, Separate Feature Channels: True, Scaling Startpoint: MEAN, Variability Measure: AD, Interpolate Phi: 1, Threshold percentile: 100, TI hashes: "easynegative: c74b4e810b03, badhandv4: 5e40d722fc3d, bad-picturenegativeembeddingforChilloutMix_75VectorVersion: 7d9cc5f549d7", Version: v1.6.0
@CMMY <lora:heyehua-000009:0.2>,这个LORA 能给个链接吗？？？？
@xyz13019419960771 我自己训练的脸模不能给
请问你的Lora是用什么大模型训练的？我下载Lora用几个模型生成的图片效果都不太好
sd1.5
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.